Lie24/Role_LLM_Cube_v1
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: Lie24/Role_LLM_Cube_v1
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-28 18:19:05 +08:00
commit 5cc4441c3f
25 changed files with 416959 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text

3
README.md Normal file
View File

@@ -0,0 +1,3 @@
---
license: mit
---

39
config.json Normal file
View File

@@ -0,0 +1,39 @@
{
"_name_or_path": "/home/llama/zxl_2024/model/Meta-Llama-3.1-8B-Instruct",
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 128000,
"eos_token_id": [
128001,
128008,
128009
],
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 131072,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": {
"factor": 8.0,
"high_freq_factor": 4.0,
"low_freq_factor": 1.0,
"original_max_position_embeddings": 8192,
"rope_type": "llama3"
},
"rope_theta": 500000.0,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.43.3",
"use_cache": false,
"vocab_size": 128256
}

12
generation_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"bos_token_id": 128000,
"do_sample": true,
"eos_token_id": [
128001,
128008,
128009
],
"temperature": 0.6,
"top_p": 0.9,
"transformers_version": "4.43.3"
}

1
latest Normal file
View File

@@ -0,0 +1 @@
global_step470

3
model-00001-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:41e09dd867afd1c9eee244aace92c86bde986350257ad576518a9b1561236fdf
size 4976698672

3
model-00002-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2f59bf56eb6da1a02070d0ad9767077f8e999855a6ab80b085f8998dcc942fe4
size 4999802720

3
model-00003-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0c6f9b2b528248059f9e5d2204386d021f89cf7f2ffda773182021cb37baabde
size 4915916176

3
model-00004-of-00004.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3ff9e60b4629dfccbbb23fdc0f22e152d002791e891f7f40e628ef7921f44c3b
size 1168138808

298
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,298 @@
{
"metadata": {
"total_size": 16060522496
},
"weight_map": {
"lm_head.weight": "model-00004-of-00004.safetensors",
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
"model.norm.weight": "model-00004-of-00004.safetensors"
}
}

3
rng_state_0.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e805f7217f63010632b2b4605b402af57dabb5e938c9fd5a093f93c3bff4a8d6
size 15984

3
rng_state_1.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a4efe3c1481eb46beecd61f4c325e90c8788e1008477f6bd8ce5ed6a13766073
size 15984

3
rng_state_2.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3d1528b4d9942dbfd04d6dcd4d008518a9fb5097d58ef1b34436fbc6bebca1f5
size 15984

3
rng_state_3.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7dd04a02e45c9e68776b5d1b3d526f1818ff6f41c56e43018624996e3c2ed3b5
size 15984

3
rng_state_4.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b99762fa9047166535b4ae6c3edd2abe15f2befffdf88abe2e81588caec257b2
size 15984

3
rng_state_5.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d6024bff333c8a669afca3c5892fb3ebfbc6f204c384d68a636ae8c749f155b6
size 15984

3
rng_state_6.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7f38bc9ba167d09d01ca2dc8bb5778e6cf48ac482f233002a0bc699f6a45ce03
size 15984

3
rng_state_7.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4faff9d45205b3536a2145f29972cf13b59b037592c8f3400a327298aa274c9a
size 15984

3
scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a3415aa6316c9441283b2c4be1fdba64505aa431e8d7e54bd9f87a1f9e616c8b
size 1064

17
special_tokens_map.json Normal file
View File

@@ -0,0 +1,17 @@
{
"bos_token": {
"content": "<|begin_of_text|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<|eot_id|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": "<|eot_id|>"
}

410504
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

2065
tokenizer_config.json Normal file
View File

File diff suppressed because it is too large Load Diff

3339
trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:614ec794012e3514795bf6ac328362619f266d50790b4723c1bcfbfc84cf931d
size 7096

604
zero_to_fp32.py Normal file
View File

@@ -0,0 +1,604 @@
#!/usr/bin/env python
# Copyright (c) Microsoft Corporation.
# SPDX-License-Identifier: Apache-2.0
# DeepSpeed Team
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
# application.
#
# example: python zero_to_fp32.py . pytorch_model.bin
import argparse
import torch
import glob
import math
import os
import re
from collections import OrderedDict
from dataclasses import dataclass
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
# DeepSpeed data structures it has to be available in the current python environment.
from deepspeed.utils import logger
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
@dataclass
class zero_model_state:
buffers: dict()
param_shapes: dict()
shared_params: list
ds_version: int
frozen_param_shapes: dict()
frozen_param_fragments: dict()
debug = 0
# load to cpu
device = torch.device('cpu')
def atoi(text):
return int(text) if text.isdigit() else text
def natural_keys(text):
'''
alist.sort(key=natural_keys) sorts in human order
http://nedbatchelder.com/blog/200712/human_sorting.html
(See Toothy's implementation in the comments)
'''
return [atoi(c) for c in re.split(r'(\d+)', text)]
def get_model_state_file(checkpoint_dir, zero_stage):
if not os.path.isdir(checkpoint_dir):
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
# there should be only one file
if zero_stage <= 2:
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
elif zero_stage == 3:
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
if not os.path.exists(file):
raise FileNotFoundError(f"can't find model states file at '{file}'")
return file
def get_checkpoint_files(checkpoint_dir, glob_pattern):
# XXX: need to test that this simple glob rule works for multi-node setup too
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
if len(ckpt_files) == 0:
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
return ckpt_files
def get_optim_files(checkpoint_dir):
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
def get_model_state_files(checkpoint_dir):
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
def parse_model_states(files):
zero_model_states = []
for file in files:
state_dict = torch.load(file, map_location=device)
if BUFFER_NAMES not in state_dict:
raise ValueError(f"{file} is not a model state checkpoint")
buffer_names = state_dict[BUFFER_NAMES]
if debug:
print("Found buffers:", buffer_names)
# recover just the buffers while restoring them to fp32 if they were saved in fp16
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
param_shapes = state_dict[PARAM_SHAPES]
# collect parameters that are included in param_shapes
param_names = []
for s in param_shapes:
for name in s.keys():
param_names.append(name)
# update with frozen parameters
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
if frozen_param_shapes is not None:
if debug:
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
param_names += list(frozen_param_shapes.keys())
# handle shared params
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
ds_version = state_dict.get(DS_VERSION, None)
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
z_model_state = zero_model_state(buffers=buffers,
param_shapes=param_shapes,
shared_params=shared_params,
ds_version=ds_version,
frozen_param_shapes=frozen_param_shapes,
frozen_param_fragments=frozen_param_fragments)
zero_model_states.append(z_model_state)
return zero_model_states
def parse_optim_states(files, ds_checkpoint_dir):
total_files = len(files)
state_dicts = []
for f in files:
state_dict = torch.load(f, map_location=device)
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
# and also handle the case where it was already removed by another helper script
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
state_dicts.append(state_dict)
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
raise ValueError(f"{files[0]} is not a zero checkpoint")
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
# parameters can be different from data parallelism for non-expert parameters. So we can just
# use the max of the partition_count to get the dp world_size.
if type(world_size) is list:
world_size = max(world_size)
if world_size != total_files:
raise ValueError(
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
)
# the groups are named differently in each stage
if zero_stage <= 2:
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
elif zero_stage == 3:
fp32_groups_key = FP32_FLAT_GROUPS
else:
raise ValueError(f"unknown zero stage {zero_stage}")
if zero_stage <= 2:
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
elif zero_stage == 3:
# if there is more than one param group, there will be multiple flattened tensors - one
# flattened tensor per group - for simplicity merge them into a single tensor
#
# XXX: could make the script more memory efficient for when there are multiple groups - it
# will require matching the sub-lists of param_shapes for each param group flattened tensor
fp32_flat_groups = [
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
]
return zero_stage, world_size, fp32_flat_groups
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
"""
Returns fp32 state_dict reconstructed from ds checkpoint
Args:
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
"""
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
optim_files = get_optim_files(ds_checkpoint_dir)
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
model_files = get_model_state_files(ds_checkpoint_dir)
zero_model_states = parse_model_states(model_files)
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
if zero_stage <= 2:
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
exclude_frozen_parameters)
elif zero_stage == 3:
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
exclude_frozen_parameters)
def _zero2_merge_frozen_params(state_dict, zero_model_states):
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
return
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
if debug:
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
wanted_params = len(frozen_param_shapes)
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
print(f'Frozen params: Have {avail_numel} numels to process.')
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
total_params = 0
total_numel = 0
for name, shape in frozen_param_shapes.items():
total_params += 1
unpartitioned_numel = shape.numel()
total_numel += unpartitioned_numel
state_dict[name] = frozen_param_fragments[name]
if debug:
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
def _has_callable(obj, fn):
attr = getattr(obj, fn, None)
return callable(attr)
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
param_shapes = zero_model_states[0].param_shapes
# Reconstruction protocol:
#
# XXX: document this
if debug:
for i in range(world_size):
for j in range(len(fp32_flat_groups[0])):
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
# XXX: memory usage doubles here (zero2)
num_param_groups = len(fp32_flat_groups[0])
merged_single_partition_of_fp32_groups = []
for i in range(num_param_groups):
merged_partitions = [sd[i] for sd in fp32_flat_groups]
full_single_fp32_vector = torch.cat(merged_partitions, 0)
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
avail_numel = sum(
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
if debug:
wanted_params = sum([len(shapes) for shapes in param_shapes])
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
# not asserting if there is a mismatch due to possible padding
print(f"Have {avail_numel} numels to process.")
print(f"Need {wanted_numel} numels in {wanted_params} params.")
# params
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
# out-of-core computing solution
total_numel = 0
total_params = 0
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
offset = 0
avail_numel = full_single_fp32_vector.numel()
for name, shape in shapes.items():
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
total_numel += unpartitioned_numel
total_params += 1
if debug:
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
offset += unpartitioned_numel
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
# live optimizer object, so we are checking that the numbers are within the right range
align_to = 2 * world_size
def zero2_align(x):
return align_to * math.ceil(x / align_to)
if debug:
print(f"original offset={offset}, avail_numel={avail_numel}")
offset = zero2_align(offset)
avail_numel = zero2_align(avail_numel)
if debug:
print(f"aligned offset={offset}, avail_numel={avail_numel}")
# Sanity check
if offset != avail_numel:
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
exclude_frozen_parameters):
state_dict = OrderedDict()
# buffers
buffers = zero_model_states[0].buffers
state_dict.update(buffers)
if debug:
print(f"added {len(buffers)} buffers")
if not exclude_frozen_parameters:
_zero2_merge_frozen_params(state_dict, zero_model_states)
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
# recover shared parameters
for pair in zero_model_states[0].shared_params:
if pair[1] in state_dict:
state_dict[pair[0]] = state_dict[pair[1]]
return state_dict
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
remainder = unpartitioned_numel % world_size
padding_numel = (world_size - remainder) if remainder else 0
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
return partitioned_numel, padding_numel
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
return
if debug:
for i in range(world_size):
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
wanted_params = len(frozen_param_shapes)
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
print(f'Frozen params: Have {avail_numel} numels to process.')
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
total_params = 0
total_numel = 0
for name, shape in zero_model_states[0].frozen_param_shapes.items():
total_params += 1
unpartitioned_numel = shape.numel()
total_numel += unpartitioned_numel
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
if debug:
print(
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
)
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
param_shapes = zero_model_states[0].param_shapes
avail_numel = fp32_flat_groups[0].numel() * world_size
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
# param, re-consolidating each param, while dealing with padding if any
# merge list of dicts, preserving order
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
if debug:
for i in range(world_size):
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
wanted_params = len(param_shapes)
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
# not asserting if there is a mismatch due to possible padding
avail_numel = fp32_flat_groups[0].numel() * world_size
print(f"Trainable params: Have {avail_numel} numels to process.")
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
# params
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
# out-of-core computing solution
offset = 0
total_numel = 0
total_params = 0
for name, shape in param_shapes.items():
unpartitioned_numel = shape.numel()
total_numel += unpartitioned_numel
total_params += 1
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
if debug:
print(
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
)
# XXX: memory usage doubles here
state_dict[name] = torch.cat(
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
0).narrow(0, 0, unpartitioned_numel).view(shape)
offset += partitioned_numel
offset *= world_size
# Sanity check
if offset != avail_numel:
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
exclude_frozen_parameters):
state_dict = OrderedDict()
# buffers
buffers = zero_model_states[0].buffers
state_dict.update(buffers)
if debug:
print(f"added {len(buffers)} buffers")
if not exclude_frozen_parameters:
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
# recover shared parameters
for pair in zero_model_states[0].shared_params:
if pair[1] in state_dict:
state_dict[pair[0]] = state_dict[pair[1]]
return state_dict
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
"""
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
via a model hub.
Args:
- ``checkpoint_dir``: path to the desired checkpoint folder
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
- ``exclude_frozen_parameters``: exclude frozen parameters
Returns:
- pytorch ``state_dict``
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
the checkpoint.
A typical usage might be ::
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
# do the training and checkpoint saving
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
model = model.cpu() # move to cpu
model.load_state_dict(state_dict)
# submit to model hub or save the model to share with others
In this example the ``model`` will no longer be usable in the deepspeed context of the same
application. i.e. you will need to re-initialize the deepspeed engine, since
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
"""
if tag is None:
latest_path = os.path.join(checkpoint_dir, 'latest')
if os.path.isfile(latest_path):
with open(latest_path, 'r') as fd:
tag = fd.read().strip()
else:
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
if not os.path.isdir(ds_checkpoint_dir):
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None, exclude_frozen_parameters=False):
"""
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
Args:
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
- ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
- ``exclude_frozen_parameters``: exclude frozen parameters
"""
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
print(f"Saving fp32 state dict to {output_file}")
torch.save(state_dict, output_file)
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
"""
1. Put the provided model to cpu
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
3. Load it into the provided model
Args:
- ``model``: the model object to update
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
Returns:
- ``model`: modified model
Make sure you have plenty of CPU memory available before you call this function. If you don't
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
conveniently placed for you in the checkpoint folder.
A typical usage might be ::
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
# submit to model hub or save the model to share with others
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
"""
logger.info(f"Extracting fp32 weights")
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
logger.info(f"Overwriting model with fp32 weights")
model = model.cpu()
model.load_state_dict(state_dict, strict=False)
return model
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("checkpoint_dir",
type=str,
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
parser.add_argument(
"output_file",
type=str,
help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
parser.add_argument("-t",
"--tag",
type=str,
default=None,
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
args = parser.parse_args()
debug = args.debug
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
args.output_file,
tag=args.tag,
exclude_frozen_parameters=args.exclude_frozen_parameters)